© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5399
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup

    oai_token-act-pair · gemini-2.0-flash

    mathrm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     K
    -0.52
     \
    -0.50
     C
    -0.48
     k
    -0.44
     
    -0.43
     $\
    -0.42
     N
    -0.42
     for
    -0.42
    ↵↵
    -0.41
     E
    -0.40
    POSITIVE LOGITS
    ^(@)
    0.86
     Efq
    0.85
     ***/
    0.82
     }</
    0.80
     ―――――
    0.80
    ,:);
    0.80
     ]
    0.79
     itſelf
    0.75
     myſelf
    0.75
     **/
    0.73
    Activations Density 0.531%

    No Known Activations